Audit a historical text corpus
Preserve source ebooks and licenses, inspect chapter boundaries and make tokenization decisions visible.
numpy · pandas · matplotlib · IPython
HUMANITIES / 01–06
Humanities & social sciences
6 independent, runnable lessons connecting questions, traceable inputs, transparent methods and interpretation. One notebook download starts each workflow.
Learning path 01 → 02 → 03 → 04 → 05 → 06; every lesson also runs independently.
Download this discipline in both languages6 recipes
Compare length-controlled lexical diversity
Separate whole-corpus token/type counts from matched-window vocabulary ratios and inspect length effects.
numpy · pandas · matplotlib · IPython
Read keyword frequencies in context
Retrieve every exact-token match with context, inspect chapter-normalized counts and return to the source passages.
numpy · pandas · matplotlib · IPython
Audit a name-mention cooccurrence graph
Declare surface-pattern aliases, count paragraph cooccurrences and inspect threshold-sensitive graph summaries.
numpy · pandas · matplotlib · networkx · IPython
Inspect TF-IDF and signed chapter projections
Build a declared chapter vocabulary, compute normalized TF-IDF and interpret an uncentered SVD without treating axes as topic probabilities.
numpy · pandas · matplotlib · IPython
Explore dated social indicators with explicit scope
Join economy-level income, population and life-expectancy observations, audit missingness and distinguish association from individual or causal inference.
numpy · pandas · scipy · matplotlib · IPython
No matching recipes. Try another query or topic.